© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112047
    Prev
    Next
    INDEX
    Explanations

    syncope, synuclein, synced

    np_acts-logits-general · gemini-2.5-flash-lite

    words beginning with "syn-" like "synapse," "synced," "synucle," or "synopsis."

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron selectively activates on tokens containing the character sequence “syn,” i.e. words that begin with or include the prefix “syn.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </strong>
    -3.67
     poderão
    -2.67
    </em>
    -2.59
     womit
    -2.58
     who
    -2.45
    鹮
    -2.42
     I
    -2.42
     encontram
    -2.28
     houve
    -2.22
    </h4>
    -2.20
    POSITIVE LOGITS
    \
    3.86
    ⢪
    2.58
    敍
    2.50
     debilitating
    2.44
     hés
    2.44
    𐍆
    2.39
    摑
    2.39
     美味
    2.38
     店内
    2.34
     enviado
    2.33
    Activations Density 0.010%

    No Known Activations